{"id":"https://openalex.org/W4398151388","doi":"https://doi.org/10.1109/access.2024.3402736","title":"Acoustic-Scene-Aware Target Sound Separation With Sound Embedding Refinement","display_name":"Acoustic-Scene-Aware Target Sound Separation With Sound Embedding Refinement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4398151388","doi":"https://doi.org/10.1109/access.2024.3402736"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3402736","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3402736","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10534351.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10534351.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049167445","display_name":"Yungyeo Kim","orcid":"https://orcid.org/0009-0008-9858-453X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yungyeo Kim","raw_affiliation_strings":["Department of Electronic Engineering, Hanyang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Department of Electronic Engineering, Hanyang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049167445"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.0513,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74375298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"71606","last_page":"71616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7547640800476074},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.7046420574188232},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5576874613761902},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.5563579201698303},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5552718043327332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5333212614059448},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.511434018611908},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.489940345287323},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46322062611579895},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.43041738867759705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3769330680370331},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33390867710113525},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.19970351457595825},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0882723331451416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547640800476074},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7046420574188232},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5576874613761902},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.5563579201698303},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5552718043327332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5333212614059448},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.511434018611908},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.489940345287323},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46322062611579895},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.43041738867759705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3769330680370331},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33390867710113525},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.19970351457595825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0882723331451416},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3402736","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3402736","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10534351.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:09eb5807e895480ca80c77b1006018ab","is_oa":true,"landing_page_url":"https://doaj.org/article/09eb5807e895480ca80c77b1006018ab","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 71606-71616 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3402736","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3402736","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10534351.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G377792351","display_name":null,"funder_award_id":"RS-2023-00302424","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4398151388.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2127851351","https://openalex.org/W2760103357","https://openalex.org/W2771361008","https://openalex.org/W2792643794","https://openalex.org/W2939084498","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2972568703","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W2981436548","https://openalex.org/W2990666817","https://openalex.org/W2998657200","https://openalex.org/W3015199127","https://openalex.org/W3016038135","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3095263845","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3160972914","https://openalex.org/W3163652268","https://openalex.org/W4205689591","https://openalex.org/W4224871700","https://openalex.org/W4224914418","https://openalex.org/W4256399001","https://openalex.org/W4285207286","https://openalex.org/W4289665794","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4313855693","https://openalex.org/W4367597591","https://openalex.org/W4372260051","https://openalex.org/W4385245566","https://openalex.org/W4386765318","https://openalex.org/W4389356607","https://openalex.org/W4393712683","https://openalex.org/W6631190155","https://openalex.org/W6749029207","https://openalex.org/W6780226713","https://openalex.org/W6784499681","https://openalex.org/W6801037760","https://openalex.org/W6802966285"],"related_works":["https://openalex.org/W2077498359","https://openalex.org/W1608003482","https://openalex.org/W2903040254","https://openalex.org/W1522062127","https://openalex.org/W2074134755","https://openalex.org/W4226449293","https://openalex.org/W606675693","https://openalex.org/W2117408192","https://openalex.org/W2943743938","https://openalex.org/W2088740872"],"abstract_inverted_index":{"Target":[0,119],"sound":[1,86,96,120,123,130,166,198],"separation":[2,121,138,177,199],"(TSS)":[3],"aims":[4],"to":[5,35,135,161],"separate":[6],"specific":[7,140],"sounds":[8,31,61,73,142,181],"of":[9,52,59,71,87,106,139,178,191],"interest,":[10],"like":[11],"a":[12,15,88,98,104,110,114,150],"speech":[13],"or":[14],"musical":[16],"instrument,":[17],"from":[18,103],"complex":[19],"acoustic":[20,45,67,81,154,184],"environments":[21],"with":[22,122],"multiple":[23,151],"overlapping":[24],"sounds.":[25,108],"In":[26],"realistic":[27],"scenarios,":[28],"the":[29,43,50,65,79,85,94,137,145,172,176,189],"important":[30],"that":[32,196],"we":[33,112],"want":[34],"hear":[36],"can":[37],"differ":[38],"depending":[39],"on":[40,78,144],"transitions":[41],"in":[42,97],"surrounding":[44,146],"scene.":[46,147],"This":[47],"study":[48],"addresses":[49],"problem":[51],"acoustic-scene-aware":[53,133],"TSS,":[54],"which":[55],"separates":[56],"predefined":[57,92],"sets":[58,70],"target":[60,72,95,141,180],"considered":[62],"significant":[63],"for":[64,158,171],"current":[66],"environment.":[68],"Predefined":[69],"were":[74],"determined":[75],"beforehand":[76],"based":[77,143],"expected":[80],"scenes.":[82,185],"For":[83],"example,":[84],"bicycle":[89],"bell":[90],"is":[91],"as":[93,169],"park":[99],"scene":[100,155,162,201],"and":[101,200],"separated":[102],"mixture":[105],"various":[107,183],"As":[109],"solution,":[111],"propose":[113],"novel":[115],"approach":[116,195],"called":[117],"Acoustic-SCene-Aware":[118],"Embedding":[124],"Refinement":[125],"(SCATER).":[126],"It":[127],"refines":[128],"pre-trained":[129],"embeddings":[131,167],"into":[132],"representations":[134],"guide":[136],"SCATER":[148,192],"adopts":[149],"instance":[152],"learning-based":[153],"classification":[156,202],"system":[157],"rapid":[159],"response":[160],"changes.":[163],"The":[164],"refined":[165],"serve":[168],"cues":[170],"TSS":[173],"model,":[174],"enabling":[175],"different":[179],"across":[182],"Experimental":[186],"results":[187],"demonstrate":[188],"superiority":[190],"over":[193],"an":[194],"combines":[197],"separately.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}